Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 760 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.8019. Min Act: -0.0001

Data Index: 674468 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1167520 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6598. Min Act: -0.0000

Data Index: 461529 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.7385. Min Act: -0.0000

Data Index: 673597 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6380. Min Act: -0.0000

Data Index: 300862 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6762. Min Act: -0.0000

Data Index: 497359 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6079. Min Act: -0.0000

Data Index: 972586 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6216. Min Act: -0.0000

Data Index: 302713 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6258. Min Act: -0.0001

Data Index: 659352 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1175204 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5732. Min Act: -0.0001

Data Index: 207339 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5586. Min Act: -0.0001

Data Index: 412858 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5517. Min Act: -0.0000

Data Index: 692479 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1219178 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5407. Min Act: -0.0000

Data Index: 422568 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5655. Min Act: -0.0000

Data Index: 571838 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.4999. Min Act: -0.0000

Data Index: 564192 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1154912 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1233387 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1068377 (C4 (Web Text))

Max Activating Token Index: 244